
import pandas as pd
import geopandas as gpd
import matplotlib.pyplot as plt
import plotly.express as px
import plotly
import numpy as np
import json
import folium
import folium.plugins as plugins
from bokeh.plotting import figure, output_file, save
from bokeh.io import output_notebook, show
from bokeh.models import Div, HoverTool, Select, CustomJS, GeoJSONDataSource, AutocompleteInput, Label
from bokeh.models.widgets import CheckboxGroup
from datetime import datetime, timedelta, time
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn import metrics
from matplotlib import cm
import matplotlib.colors as mcolors


output_notebook()


plotly.offline.init_notebook_mode()


# Reading in NYC 311 Service Requests dataset, from the year 2023
data = pd.read_csv('311_Noise_Complaints_2023.csv')
data.head()

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\4118985633.py:2: DtypeWarning: Columns (31) have mixed types. Specify dtype option on import or set low_memory=False.
  data = pd.read_csv('311_Noise_Complaints_2023.csv')


# Reading in Department of Buildings (DOB) Permits dataset
path= r"DOB_Permit_Issuance_20240421.csv"
permit_data = pd.read_csv(path)
permit_data.head()


# Read in data
data_party = pd.read_csv('house_party_complaints_2010_2023.csv')

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\3451936411.py:2: DtypeWarning: Columns (15,17,18,20) have mixed types. Specify dtype option on import or set low_memory=False.
  data_party = pd.read_csv('house_party_complaints_2010_2023.csv')


# Function to turn a datetime object to integer represantion of time, in form of minutes that passed until last noon (12 p.m.)
def minutes_since_noon(dt):
    if dt.time() < time(12, 0):
        delta = dt - datetime.combine(dt.date() - timedelta(days=1), time(12, 0))
    else:
        delta = dt - datetime.combine(dt.date(), time(12, 0))
    return delta.seconds // 60

# Convert to datetime
data_party['Created Date'] = pd.to_datetime(data_party['Created Date'], format="%m/%d/%Y %I:%M:%S %p")
data_party['Closed Date'] = pd.to_datetime(data_party['Closed Date'], format="%m/%d/%Y %I:%M:%S %p")

# Remove unnecessary columns
data_party = data_party.drop(columns=['Vehicle Type', 'Taxi Company Borough', 'Taxi Pick Up Location', 'Bridge Highway Name', 'Bridge Highway Direction',
                            'Road Ramp', 'Bridge Highway Segment', 'Park Borough', 'Park Facility Name', 'BBL', 'Community Board', 'Descriptor',
                            'Location Type', 'Complaint Type', 'Landmark','Facility Type','Due Date'],
                            errors='ignore')

# Uncapitalize borough names (e.g. from BRONX to Bronx)
data_party.Borough = data_party.Borough.str.title()

# Remove empty zip codes
data_party = data_party[~data_party['Incident Zip'].isnull()]

# Add date columns
data_party['Month'] = data_party['Created Date'].dt.month
data_party['Weekday'] = data_party['Created Date'].dt.weekday
data_party['Time'] = data_party['Created Date'].apply(minutes_since_noon)

# Remove duplicate complaints for the same location the same night, but keep the count
data_party['Adjusted Date'] = data_party['Created Date'].apply(lambda dt: dt.date() if dt.time() > pd.Timestamp('07:00:00').time() else (dt - pd.Timedelta(days=1)).date())
data_party = data_party.sort_values('Created Date')
grouped = data_party.groupby(['Adjusted Date', 'Incident Address']).size().reset_index(name='Complaints Count')
data_party = pd.merge(left=data_party, right=grouped)
data_party = data_party.drop_duplicates(subset=['Adjusted Date', 'Incident Address'])

# Print out head
data_party.head()


# Total size
print(f"Number of rows: {data_party.shape[0]}")
print(f"Number of columns: {data_party.shape[1]}")

Number of rows: 1447394
Number of columns: 29


# Columns that were left
print(data_party.columns.values)

['Unique Key' 'Created Date' 'Closed Date' 'Agency' 'Agency Name'
 'Incident Zip' 'Incident Address' 'Street Name' 'Cross Street 1'
 'Cross Street 2' 'Intersection Street 1' 'Intersection Street 2'
 'Address Type' 'City' 'Status' 'Resolution Description'
 'Resolution Action Updated Date' 'Borough' 'X Coordinate (State Plane)'
 'Y Coordinate (State Plane)' 'Open Data Channel Type' 'Latitude'
 'Longitude' 'Location' 'Month' 'Weekday' 'Time' 'Adjusted Date'
 'Complaints Count']


# Date range
min_date = data_party['Created Date'].min()
max_date = data_party['Created Date'].max()
date_range = max_date - min_date
print(f"Date range: {date_range.days} days, from {min_date} to {max_date}")

Date range: 5112 days, from 2010-01-01 00:08:02 to 2023-12-31 23:58:16


# Quick look at the number of complaints
with open('new-york-zip-codes-_1604.geojson') as file:
    nyc_zips = json.load(file)

grouped_zip = data_party.groupby(['Incident Zip']).size().reset_index(name='count')
max_val = max(grouped_zip['count'])
min_val = min(grouped_zip['count'])
lat = data_party.Latitude.mean()
lon = data_party.Longitude.mean()
fig = px.choropleth_mapbox(grouped_zip, 
                           geojson=nyc_zips, 
                           locations='Incident Zip', 
                           featureidkey='properties.ZCTA5CE10',
                           color='count',
                           mapbox_style="carto-positron",
                           zoom=9, 
                           center = {"lat": lat, "lon": lon},
                           range_color=(min_val, max_val),
                           color_continuous_scale="Oranges",
                           opacity=0.5
                          )

fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()


data_grouped = data_party.groupby(['Incident Zip']).size().reset_index(name='NoiseComplaints')
plt.hist(data_grouped['NoiseComplaints'], bins=50)
plt.title('Distribution of Noise Complaints in ZIP areas')
plt.xlabel('Nr of complaints')
plt.ylabel('Frequency')
plt.show()


# Total size of the dataset NYC 311 Service Requests
print(f"Number of rows: {data.shape[0]}")
print(f"Number of columns: {data.shape[1]}")

Number of rows: 686231
Number of columns: 41


columns_to_drop = ["Taxi Company Borough", "Taxi Pick Up Location", 
                   "Bridge Highway Name", "Bridge Highway Direction", 
                   "Road Ramp", "Bridge Highway Segment", "Due Date", 
                   "Facility Type", "Vehicle Type"]

data = data.drop(columns=columns_to_drop)


# Duplicated rows
duplicate_rows = data[data.duplicated()]
print("Duplicate rows:")

Duplicate rows:


unique_types = data['Descriptor'].nunique()
print(f"Number of unique types: {unique_types}")
# print(noise_data['Descriptor'].unique())

descriptor_counts = data.groupby('Descriptor').size()
# Sort the counts in descending order
descriptor_counts_sorted = descriptor_counts.sort_values(ascending=False)
print(descriptor_counts_sorted)

Number of unique types: 24
Descriptor
Loud Music/Party                                        353547
Banging/Pounding                                        103549
Loud Talking                                             58725
Other                                                    57312
Car/Truck Music                                          34239
Noise: Construction Before/After Hours (NM1)             21752
Engine Idling                                            10349
Car/Truck Horn                                            9047
Noise: Construction Equipment (NC1)                       8056
Noise, Barking Dog (NR5)                                  7737
Loud Television                                           5002
Noise: Alarms (NR3)                                       4360
Noise: air condition/ventilation equipment (NV1)          4211
Noise: Jack Hammering (NC2)                               2398
Noise, Ice Cream Truck (NR4)                              1539
News Gathering                                            1094
Noise:  lawn care equipment (NCL)                         1083
Noise: Private Carting Noise (NQ1)                         841
NYPD                                                       721
Noise, Other Animals (NR6)                                 268
Noise: Boat(Engine,Music,Etc) (NR10)                       248
Noise: Manufacturing Noise (NK1)                           118
Noise: Other Noise Sources (Use Comments) (NZZ)             34
Noise: Loud Music/Daytime (Mark Date And Time) (NN1)         1
dtype: int64


# Define list of construction related descriptors
construction_noise_complains = ['Noise: Construction Before/After Hours (NM1)', 'Noise: Construction Equipment (NC1)', 'Noise: Jack Hammering (NC2)']
data = data[data['Descriptor'].isin(construction_noise_complains)]
# Drop that data that doesn't have Latitude, Longitude fields.
data = data.dropna(subset=['Latitude', 'Longitude'], inplace=False)
print(f"Total number of observations inside construction-noise related data: {len(data)}")

Total number of observations inside construction-noise related data: 31615


# Standardizing Data Formats

data['Created Date'] = pd.to_datetime(data['Created Date'], format="%m/%d/%Y %I:%M:%S %p")
data['Closed Date'] = pd.to_datetime(data['Closed Date'], format="%m/%d/%Y %I:%M:%S %p")


# Date range

min_date = data['Created Date'].min()
max_date = data['Created Date'].max()
date_range = max_date - min_date
print(f"Date range: {date_range.days} days, from {min_date} to {max_date}")

Date range: 364 days, from 2023-01-01 08:38:00 to 2023-12-31 18:02:00


# Standardizing Data Formats
permit_data['Filing Date'] = pd.to_datetime(permit_data['Filing Date'], format="%m/%d/%Y")
permit_data['Expiration Date'] = pd.to_datetime(permit_data['Expiration Date'], format="%m/%d/%Y")
permit_data['Issuance Date'] = pd.to_datetime(permit_data['Issuance Date'], format="%m/%d/%Y")
permit_data['Job Start Date'] = pd.to_datetime(permit_data['Job Start Date'], format="%m/%d/%Y")
permit_data['Owner\'s Business Name'] = permit_data['Owner\'s Business Name'].replace('NYCSCA', 'NYC SCA')
permit_data = permit_data.dropna(subset=['LATITUDE', 'LONGITUDE'], inplace=False)


# Total size of DOB permit data
print(f"Number of rows: {permit_data.shape[0]}")
print(f"Number of columns: {permit_data.shape[1]}")

# Other properties
min_date = permit_data['Job Start Date'].min()
max_date = permit_data['Job Start Date'].max()
date_range = max_date - min_date
print(f"Job permits for date range: {date_range.days} days, from {min_date} to {max_date}")

unique_types = permit_data['Permittee\'s Business Name'].nunique()
print(f"Number of unique companies that received permits: {unique_types}")

Number of rows: 14424
Number of columns: 60
Job permits for date range: 361 days, from 2023-01-02 00:00:00 to 2023-12-29 00:00:00
Number of unique companies that received permits: 1360


print(f"Most interesting columns inside the Permit Dataset\n")
print(f"{permit_data[['Job Start Date', 'BOROUGH', 'Job #', 'LATITUDE', 'LONGITUDE']].head()}")

Most interesting columns inside the Permit Dataset

  Job Start Date        BOROUGH      Job #   LATITUDE  LONGITUDE
0     2023-11-21       BROOKLYN  321953891  40.681528 -73.957603
1     2023-11-21       BROOKLYN  340905275  40.609957 -74.008655
2     2023-05-01  STATEN ISLAND  540246134  40.583785 -74.093882
3     2023-05-01  STATEN ISLAND  540249337  40.640468 -74.083137
4     2023-11-21       BROOKLYN  340906087  40.654432 -73.940354


# First we created some helper dictionary structures

zip_borough_dict = {
    'Queens': [],
    'Bronx': [],
    'Brooklyn': [],
    'Staten Island': [],
    'Manhattan': [],
}

zip_to_borough = {}

def find_borough(zip):
    if zip=='11208' or zip=='11237':
        return 'Brooklyn'
    if zip == '11421':
        return 'Queens'
    if zip=='10463':
        return 'Bronx'
    return 'Unspecified'

# Fill the dictionary and assing correct borough if it's "Unspecified"
for index, row in data_party.iterrows():
    borough = row['Borough']
    zip_code = str(int(row['Incident Zip']))
    if borough=='Unspecified':
        borough = find_borough(zip_code)
        data_party.at[index, 'Borough'] = borough
    if zip_code not in zip_borough_dict[borough]:
        zip_borough_dict[borough].append(zip_code)
    if zip_code not in zip_to_borough:
        zip_to_borough[zip_code] = borough

# Remove not real ZIPs and sort data
zip_borough_dict['Manhattan'].remove('83')
zip_borough_dict['Manhattan'].remove('12345')
for key,zips in zip_borough_dict.items():
    zip_borough_dict[key] = sorted(zips)


# Create a machine learning model

X = data_party[['Month', 'Weekday', 'Incident Zip']]
y = data_party['Time']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = RandomForestRegressor(n_estimators=300, random_state=42)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, y_pred))
print('Mean Squared Error:', metrics.mean_squared_error(y_test, y_pred))
print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))  

# Function to make a prediction based on a given month, weekday and zipcode
def predict_complaint_time(month, weekday, zipcode):
    X = pd.DataFrame({'Month': month, 'Weekday': weekday, 'Incident Zip': zipcode})
    predicted_time = model.predict(X)
    return predicted_time

# Function to convert minutes after noon to actual time
def minutes_to_time(minutes):
    noon_previous_day = datetime.combine(datetime.now().date() - timedelta(days=1), time(12, 0))
    return str((noon_previous_day + timedelta(minutes=minutes)).time())

Mean Absolute Error: 193.23640472264972
Mean Squared Error: 70597.39899049004
Root Mean Squared Error: 265.70171055243515


# We needed to create data for all possible month/weekday intersecions to pass to Bokeh 
# interactive plots (browsers cannot calclate live Python code)

gdf = gpd.read_file('new-york-zip-codes-_1604.geojson')

# Prefilter data
filtered_data = {}
for m in range(-1,13):
    if (m != 0):
        filtered_data[str(m)] = {}
        for w in range (-1,7):
            if w==-1 and m==-1:
                temp = data_party
            elif w==-1:
                temp = data_party[data_party.Month==m]
            elif m==-1:
                temp = data_party[data_party.Weekday == w]
            else:
                temp = data_party[(data_party.Weekday == w) & (data_party.Month==m)]
            temp['Incident Zip'] = temp['Incident Zip'].astype(int).astype(str)
            temp = temp.groupby(['Incident Zip']).size().reset_index(name='NoiseComplaints')
            filtered_data[str(m)][str(w)] = temp.set_index('Incident Zip')['NoiseComplaints'].to_dict()
            filtered_data[str(m)][str(w)]['max'] = temp['NoiseComplaints'].max()

# Precalculate all time predictions for all ZIPs and month/weekdays
df = pd.DataFrame(np.array(np.meshgrid(np.arange(1, 13), np.arange(7), gdf['ZCTA5CE10'].astype(str))).T.reshape(-1,3), columns=['month', 'weekday', 'zip'])
df['prediction'] = predict_complaint_time(df['month'], df['weekday'], df['zip'])
df['prediction'] = df['prediction'].apply(minutes_to_time)
nested_dict = df.groupby('month').apply(lambda x: x.groupby('weekday').apply(lambda y: y.set_index('zip')['prediction'].to_dict()).to_dict()).to_dict()

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1478489561.py:20: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


# Prepare data for Bokeh
data_grouped = data_party.groupby(['Incident Zip']).size().reset_index(name='NoiseComplaints')
data_grouped['Incident Zip'] = data_grouped['Incident Zip'].astype(int).astype(str)
gdf = gdf[gdf['ZCTA5CE10'] != '99999']
merged = gdf.merge(data_grouped, left_on='ZCTA5CE10', right_on='Incident Zip', how='inner')
merged['NoiseComplaints'].fillna(0, inplace=True)
merged['selected'] = pd.Series([True]*len(merged['ZCTA5CE10']))
merged = merged[merged['ZCTA5CE10'] != '99999']
merged = merged.drop(columns=['STATEFP10', 'GEOID10', 'CLASSFP10', 'MTFCC10', 'FUNCSTAT10', 'ALAND10', 'PARTFLG10', 'AWATER10'], errors='ignore')
merged.sort_values(by="NoiseComplaints", ascending=False).head()


# Create Bokeh interactive filter map

from bokeh.layouts import column, row

checkbox_group = CheckboxGroup(labels=gdf['ZCTA5CE10'].tolist(), active=[],inline=True)
palette = cm.get_cmap('Oranges', 256)
c_dict = {i/256.0: mcolors.rgb2hex(palette(i/256.0)) for i in range(256)}
max_val = data_grouped['NoiseComplaints'].max()

def map_color(row):
    if row['selected']:
        normalized_value = row['NoiseComplaints'] / max_val
        prev_key, prev_val = -1.0, '#ffffff'
        for key, value in c_dict.items():
            if normalized_value > prev_key and normalized_value <= key:
                return value
            prev_key = key
            prev_val = value
        return prev_val
    else:
        return '#ffffff'
    
def map_borough(row):
    return zip_to_borough[row['ZCTA5CE10']]


merged['color'] = merged.apply(map_color, axis=1)
merged['Borough'] = merged.apply(map_borough, axis=1)

geosource = GeoJSONDataSource(geojson=merged.to_json())

p = figure(title='Noise Complaints by Zip Code in NYC', plot_height=600, plot_width=720, toolbar_location=None)
p.xgrid.grid_line_color = None
p.ygrid.grid_line_color = None

x_label = Label(x=0, y=-25, x_units='screen', y_units='screen', text='Longitude', render_mode='css',
                background_fill_color='white', background_fill_alpha=0.0)

y_label = Label(x=-5, y=50, x_units='screen', y_units='screen', text='Latitude', angle=90, angle_units='deg', render_mode='css',
                 background_fill_color='white', background_fill_alpha=0.0)

p.add_layout(x_label)
p.add_layout(y_label)

zipcodes = p.patches('xs', 'ys', source=geosource, fill_color='color', line_color='black', line_width=0.25, fill_alpha=1)

p.add_tools(HoverTool(renderers=[zipcodes], tooltips=[('Zip Code', '@ZCTA5CE10'), ('Noise Complaints', '@NoiseComplaints'), ('Borough', '@Borough')]))

title_bronx = Div(text="<b>Bronx</b>", width=130)
title_queens = Div(text="<b>Queens</b>", width=130)
title_si = Div(text="<b>Staten Island</b>", width=130)
title_manh = Div(text="<b>Manhattan</b>", width=130)
title_brookl = Div(text="<b>Brooklyn</b>", width=130)
checkbox_bronx = CheckboxGroup(labels=zip_borough_dict['Bronx'], active=[], width=130)
checkbox_queens = CheckboxGroup(labels=zip_borough_dict['Queens'], active=[], width=130)
checkbox_si = CheckboxGroup(labels=zip_borough_dict['Staten Island'], active=[], width=130)
checkbox_manh = CheckboxGroup(labels=zip_borough_dict['Manhattan'], active=[], width=130)
checkbox_brookl = CheckboxGroup(labels=zip_borough_dict['Brooklyn'], active=[], width=130)
month = Select(title='Choose Month', value='-1', options=[("-1", "All"),("1", "January"), ("2", "February"), ("3", "March"), ("4", "April"), ("5", "May"), ("6", "June"), ("7", "July"), ("8", "August"), ("9", "September"), ("10", "October"), ("11", "November"), ("12", "December")])
weekday = Select(title='Choose Weekday', value='-1', options=[("-1", "All"),("0", "Monday"), ('1',"Tuesday"), ('2',"Wednesday"), ('3',"Thursday"), ('4',"Friday"), ('5',"Saturday"), ('6',"Sunday")])

month_to_label = {value: label for value, label in month.options}
weekday_to_label = {value: label for value, label in weekday.options}

callback = CustomJS(args=dict(source=geosource, c_dict=c_dict, max_val=max_val, 
                              checkbox_bronx=checkbox_bronx, 
                              checkbox_queens=checkbox_queens, 
                              checkbox_si=checkbox_si, 
                              checkbox_manh=checkbox_manh, 
                              checkbox_brookl=checkbox_brookl, 
                              month=month,
                              weekday=weekday,
                              filtered_data=filtered_data,
                              month_to_label=month_to_label,
                              weekday_to_label=weekday_to_label,
                              p=p), code="""
    var zips_to_plot = [];
    zips_to_plot.push(...checkbox_bronx.active.map(i => checkbox_bronx.labels[i]));
    zips_to_plot.push(...checkbox_queens.active.map(i => checkbox_queens.labels[i]));
    zips_to_plot.push(...checkbox_si.active.map(i => checkbox_si.labels[i]));
    zips_to_plot.push(...checkbox_manh.active.map(i => checkbox_manh.labels[i]));
    zips_to_plot.push(...checkbox_brookl.active.map(i => checkbox_brookl.labels[i]));
    let filterCriteria = (element) => zips_to_plot.includes(element.toString());
    var indexes = Array.from({length: source.data.ZCTA5CE10.length}, (_, i) => i);
    if (zips_to_plot.length!=0) {
        indexes = source.data.ZCTA5CE10.reduce((acc, element, index) => {
            if(filterCriteria(element)) {
                acc.push(index);
            }
            return acc;
        }, []);
    }
    source.data.selected = new Array(source.data.ZCTA5CE10.length).fill(false);
    indexes.map(index => source.data.selected[index] = true);
    var title = 'Noise Complaints by Zip Code in NYC for ' + zips_to_plot.length + ' zip codes'
    if (zips_to_plot.length===0) {
        title = 'Noise Complaints by Zip Code in NYC for all zip codes'
    }
    if (month.value != -1 && weekday.value != -1) {
        title = title + ', for ' + weekday_to_label[weekday.value] + 's in ' + month_to_label[month.value]
    } else if (month.value != -1) {
        title = title + ', for ' + month_to_label[month.value]
    } else if (weekday.value != -1) {
        title = title + ', for ' + weekday_to_label[weekday.value] + 's'
    }
    p.title.text = title;
    var max_value = max_val;
    if (weekday.value !== -1 || month.value !== -1) {
        max_value = filtered_data[month.value][weekday.value]['max']
    }
    
    function map_color(rowIndex) {
        var selected = source.data.selected[rowIndex];
        var noiseComplaints = source.data.NoiseComplaints[rowIndex];
        if (selected) {
            var normalized_value = noiseComplaints / max_value;
            var prev_key = -1.0;
            var prev_val = '#ffffff';
            for (var key in c_dict) {
                if (normalized_value > prev_key && normalized_value <= key) {
                    return c_dict[key];
                }
                prev_key = key;
                prev_val = c_dict[key];
            }
            return prev_val;
        } else {
            return '#ffffff';
        }
    }
    function map_noise(rowIndex) {
        if (filtered_data[month.value] && 
            filtered_data[month.value][weekday.value] && 
            filtered_data[month.value][weekday.value][source.data.ZCTA5CE10[rowIndex]]) {
            return filtered_data[month.value][weekday.value][source.data.ZCTA5CE10[rowIndex]];
        } else {
            return 0;
        }
    }
    source.data.NoiseComplaints = source.data.NoiseComplaints.map((value, index) => {
        return map_noise(index);
    });
    source.data.color = new Array(source.data.ZCTA5CE10.length).fill('#ffffff');
    indexes.map(index => source.data.color[index] = map_color(index));
    source.change.emit()
""")

month.js_on_change("value",callback)
weekday.js_on_change("value",callback)

checkbox_brookl.js_on_change('active', callback)
checkbox_bronx.js_on_change('active', callback)
checkbox_manh.js_on_change('active', callback)
checkbox_si.js_on_change('active', callback)
checkbox_queens.js_on_change('active', callback)
layout = column(children=[row(month, weekday), row(p), row(column(title_brookl, checkbox_brookl),column(title_bronx, checkbox_bronx),column(title_manh, checkbox_manh),column(title_si, checkbox_si),column(title_queens, checkbox_queens))])
output_file("party_filter.html")
save(layout)

C:\Users\poczt\AppData\Local\Temp\ipykernel_20388\1700200379.py:6: MatplotlibDeprecationWarning:

The get_cmap function was deprecated in Matplotlib 3.7 and will be removed two minor releases later. Use ``matplotlib.colormaps[name]`` or ``matplotlib.colormaps.get_cmap(obj)`` instead.

'c:\\Users\\poczt\\OneDrive\\Dokumenty\\uczelnia\\DTU_4_sem\\socialdata\\socialdata\\project\\party_filter.html'


# Create Bokeh time predictions interface
from bokeh.layouts import column, row

completions = gdf['ZCTA5CE10'].astype(str).tolist()

month = Select(title='Choose Month', value='1', options=[("1", "January"), ("2", "February"), ("3", "March"), ("4", "April"), ("5", "May"), ("6", "June"), ("7", "July"), ("8", "August"), ("9", "September"), ("10", "October"), ("11", "November"), ("12", "December")], width=200)
weekday = Select(title='Choose Weekday', value='0', options=[("0", "Monday"), ('1',"Tuesday"), ('2',"Wednesday"), ('3',"Thursday"), ('4',"Friday"), ('5',"Saturday"), ('6',"Sunday")], width=200)
zip = AutocompleteInput(completions=completions, title="Input ZIP Code", width=200)
result_text = Div(text="Input ZIP code to get a predicted noise complaint time", width=720)

month_to_label = {value: label for value, label in month.options}
weekday_to_label = {value: label for value, label in weekday.options}

callback = CustomJS(args=dict(month=month,
                              weekday=weekday,
                              month_to_label=month_to_label,
                              weekday_to_label=weekday_to_label,
                              nested_dict=nested_dict,
                              result_text=result_text,
                              zip = zip), code="""
    var text = "Input ZIP code to get a predicted noise complaint time"
    console.log(zip.value)
    if (zip.value != null && zip.value!='') {
        text = 'Predicted noise complaint time in ZIP code area '+zip.value+' for ' + weekday_to_label[weekday.value] + 's in ' + month_to_label[month.value] + ': '+nested_dict[parseInt(month.value)][parseInt(weekday.value)][zip.value]
    }
    result_text.text = text
""")

month.js_on_change("value",callback)
weekday.js_on_change("value",callback)
zip.js_on_change("value",callback)

layout = column(children=[row(month, weekday, zip),row(result_text)])
output_file("party_predict.html")
save(layout)

'c:\\Users\\poczt\\OneDrive\\Dokumenty\\uczelnia\\DTU_4_sem\\socialdata\\socialdata\\project\\party_predict.html'


# Read the dictionary from the JSON file
file_name = 'final_results.json'
with open(file_name, 'r') as f:
    complaints_dict = json.load(f)
print(f"Loaded final dict: {file_name}")
print(f"Number of keys: {len(complaints_dict.keys())}")

Loaded final dict: final_results.json
Number of keys: 7071


def group_complaints_by_owner(complaints_dict, permit_data):
    
    complaints_by_owner = {}

    for job_number, complaints in complaints_dict.items():
        # Get the owner's business name for the current job_number
        owner_name = permit_data.loc[permit_data['Job #'] == int(job_number), "Permittee's Business Name"].iloc[0]
        
        if owner_name in complaints_by_owner:
            # If the owner's business name exists, append the complaints to its corresponding list
            complaints_by_owner[owner_name].extend(complaints)
        else:
            # If the owner's business name doesn't exist, create a new key-value pair
            complaints_by_owner[owner_name] = complaints.copy()
    
    complaints_by_owner = {k: v for k, v in complaints_by_owner.items() if pd.notna(k)}
    
    return complaints_by_owner

def show_sorted_owner_dict(business_dict, num_keys=20):
    # Sort the keys based on the number of values
    sorted_keys = sorted(business_dict, key=lambda k: len(business_dict[k]), reverse=True)
    
    # Limit the number of keys to show
    sorted_keys = sorted_keys[:num_keys]
    
    for key in sorted_keys:
        num_complaints = len(business_dict[key])
        print(f"Permittee's Business Name: {key}, Number of Complaints: {num_complaints}")


business_dict = group_complaints_by_owner(complaints_dict, permit_data)


print(f"\nTop most complained companies.")
show_sorted_owner_dict(business_dict, num_keys=5)

Top most complained companies.
Permittee's Business Name: ALBA SERVICES INC, Number of Complaints: 9342
Permittee's Business Name: BROOKLYN SOLARWORKS LLC, Number of Complaints: 3778
Permittee's Business Name: PRO CUSTOM SOLAR LLC, Number of Complaints: 3684
Permittee's Business Name: SUNRUN INSTALLATION SVC, Number of Complaints: 2026
Permittee's Business Name: S & N BUILDERS INC, Number of Complaints: 1864


def count_permits_by_company(permit_data, top_n=10):
    # Group permit data by Permittee's Business Name and count the number of permits for each company
    permit_counts = permit_data["Permittee's Business Name"].value_counts().sort_values(ascending=False)
    
    # Print the number of permits issued to each company for the top n companies
    for company, count in permit_counts.head(top_n).items():
        print(f"{company}: {count} permits")

# Example usage with top 5 companies
count_permits_by_company(permit_data, top_n=5)

PRO CUSTOM SOLAR LLC: 2456 permits
SUNRUN INSTALLATION SVC: 1777 permits
CENTURION SOLAR ENERGY: 771 permits
KAMTECH RESTORATION CORP: 622 permits
VENTURE HOME SOLAR LLC: 442 permits


def plot_complaints_and_permits(business_dict, permit_data, top_n=10):
    # Get the top n companies based on the number of complaints
    top_companies = sorted(business_dict, key=lambda k: len(business_dict[k]), reverse=True)[:top_n]
    
    # Initialize lists to store complaints and permits data for each company
    complaints_counts = []
    permits_counts = []
    
    # Get the number of complaints and permits for each top company
    for company in top_companies:
        # Number of complaints
        complaints_counts.append(len(business_dict[company]))
        
        # Number of permits
        permits_counts.append(len(permit_data[permit_data["Permittee's Business Name"] == company]))
    
    # Set the width of the bars
    bar_width = 0.3
    
    # Set the positions for the bars
    index = np.arange(len(top_companies))
    plt.figure(figsize=(12, 6))
    
    # Plot the bars for complaints
    plt.bar(index, complaints_counts, bar_width, label='Complaints', color='royalblue')
    
    # Plot the bars for permits
    plt.bar(index + bar_width + 0.1, permits_counts, bar_width, label='Permits', color='orange')
    
    # Add labels, title, and legend
    plt.xlabel('Company')
    plt.ylabel('Number of Complaints')
    plt.title('Complaints and Permits by Company')
    plt.xticks(index + bar_width / 2, top_companies, rotation=45, ha='right', fontsize=11)
    plt.legend()
    
    for i in range(len(top_companies)):
        plt.text(i + bar_width + 0.1, permits_counts[i] + 5, str(permits_counts[i]), ha='center', va='bottom')
    
    plt.tight_layout()
    plt.savefig('top_baddest_companies.png', bbox_inches='tight')  # Save the plot without creating a new figure
    plt.show()

plot_complaints_and_permits(business_dict, permit_data, top_n=15)


def plot_top_complaints_on_map(complaints_dict, permit_data):

    nyc_map = folium.Map(location=[40.7128, -74.0060], zoom_start=12)

    stamen_toner_url = 'https://tiles.stadiamaps.com/tiles/stamen_toner/{z}/{x}/{y}{r}.png?api_key=dba936f3-1ed1-4864-a3c0-f0b5f0f1ec3d'
    toner_layer = folium.TileLayer(
        tiles=stamen_toner_url,
        attr='Toner Background',
        name='Toner Background',
        max_zoom=18,
        min_zoom=8,
        subdomains='abcd'
    ).add_to(nyc_map)

    colors = {
        'darkred': {'min_complaints': 450, 'range': '450 or more complaints', 'show': True},
        'orange': {'min_complaints': 400, 'max_complaints': 449, 'range': '400-499 complaints', 'show': True},
        'beige': {'min_complaints': 300, 'max_complaints': 400, 'range': '300-400 complaints', 'show': False}
    }

    # Create layer groups for each color
    layer_groups = {}
    for color, info in colors.items():
        range_info = info['range']
        showByDefault = info['show']
        layer_groups[color] = folium.FeatureGroup(name=range_info, overlay=True, show=showByDefault)

    # Iterate over the top X key-value pairs
    for job_number, companies in complaints_dict.items():
        # Look up latitude and longitude values from permit_data based on the Job#
        job_data = permit_data[permit_data['Job #'] == int(job_number)]
        if not job_data.empty:
            latitude = job_data.iloc[0]['LATITUDE']
            longitude = job_data.iloc[0]['LONGITUDE']
            street_name = job_data.iloc[0]['Street Name'] 

            # Determine the color of the marker based on the number of complaints
            color = None
            for marker_color, thresholds in colors.items():
                min_complaints = thresholds['min_complaints']
                max_complaints = thresholds.get('max_complaints', float('inf'))
                num_complaints = len(companies)
                if min_complaints <= num_complaints <= max_complaints:
                    color = marker_color
                    break
            
            # Create a marker for each complaint and add it to the corresponding layer group
            if color:
                popup_text = f"Street: {street_name} Number of Complaints: {len(companies)}"
                folium.Marker(
                    location=[latitude, longitude],
                    popup=folium.Popup(popup_text, parse_html=True),
                    icon=folium.Icon(color=color, icon='info-sign')
                ).add_to(layer_groups[color])

    # Add layer groups to the map
    for layer_group in layer_groups.values():
        layer_group.add_to(nyc_map)
    
    # Add Toner Background layer control to the map
    toner_layer.add_to(nyc_map)

    # Add layer control to the map for marker layers
    folium.LayerControl(position='topright', collapsed=False).add_to(nyc_map)

    # nyc_map.save('top_complaints_map.html')

# plot_top_complaints_on_map(complaints_dict, permit_data)


# Create a Folium map centered around your desired location
map_center = [40.7128, -74.0060]  
noise_map = folium.Map(location=map_center, zoom_start=12, tiles='Stamen Toner', attr="<a href=https://docs.stadiamaps.com/map-styles/stamen-toner//>Endless Sky</a>")
stamen_toner_url = 'https://tiles.stadiamaps.com/tiles/stamen_toner/{z}/{x}/{y}{r}.png?api_key=dba936f3-1ed1-4864-a3c0-f0b5f0f1ec3d'

folium.TileLayer(
    tiles=stamen_toner_url,
    attr='Toner Background',
    name='Toner Background',
    max_zoom=18,
    min_zoom=1,
    subdomains='abcd'
).add_to(noise_map)

# Group noise data by month of the year and extract latitude and longitude coordinates for each month
grouped_data = data.groupby(data['Created Date'].dt.month)
heat_data_by_month = [(str(month), group[['Latitude', 'Longitude']].values.tolist()) for month, group in grouped_data]

month_indicators = [f'Month: {month}' for month, _ in heat_data_by_month]

heatmap_with_time = plugins.HeatMapWithTime(
    heat_data_by_month,
    radius=6,
    min_speed=1,
    max_speed=3,
    speed_step=0.5,
    index=month_indicators,
    auto_play=True,
    max_opacity=0.8,
)

heatmap_with_time.add_to(noise_map)

# noise_map.save('noise_heatmap_with_time_by_month.html')

<folium.plugins.heat_map_withtime.HeatMapWithTime at 0x161e6c17730>

	Unique Key	Created Date	Closed Date	Agency	Agency Name	Complaint Type	Descriptor	Location Type	Incident Zip	Incident Address	...	Vehicle Type	Taxi Company Borough	Taxi Pick Up Location	Bridge Highway Name	Bridge Highway Direction	Road Ramp	Bridge Highway Segment	Latitude	Longitude	Location
0	59889383	12/31/2023 11:59:42 PM	01/01/2024 01:51:01 AM	NYPD	New York City Police Department	Noise - Street/Sidewalk	Loud Music/Party	Street/Sidewalk	11375.0	63-10 108 STREET	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	40.734695	-73.850521	(40.734694673156454, -73.85052125577377)
1	59887573	12/31/2023 11:59:39 PM	01/19/2024 02:37:37 PM	EDC	Economic Development Corporation	Noise - Helicopter	Other	Above Address	10023.0	25 WEST 73 STREET	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	40.777201	-73.976159	(40.77720102455921, -73.976158989108)
2	59893860	12/31/2023 11:59:29 PM	01/01/2024 01:51:32 AM	NYPD	New York City Police Department	Noise - Street/Sidewalk	Loud Music/Party	Street/Sidewalk	11374.0	65-09 99 STREET	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	40.729379	-73.855433	(40.72937885745978, -73.85543290785074)
3	59887231	12/31/2023 11:59:23 PM	01/01/2024 12:13:30 AM	NYPD	New York City Police Department	Noise - Street/Sidewalk	Loud Music/Party	Street/Sidewalk	11232.0	870 42 STREET	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	40.644725	-73.997622	(40.64472479285036, -73.9976217135385)
4	59889382	12/31/2023 11:59:13 PM	01/01/2024 01:50:57 AM	NYPD	New York City Police Department	Noise - Street/Sidewalk	Loud Music/Party	Street/Sidewalk	11375.0	63-10 108 STREET	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	40.734695	-73.850521	(40.734694673156454, -73.85052125577377)

	BOROUGH	Bin #	House #	Street Name	Job #	Job doc. #	Job Type	Self_Cert	Block	Lot	...	Owner’s House State	Owner’s House Zip Code	Owner's Phone #	DOBRunDate	PERMIT_SI_NO	LATITUDE	LONGITUDE	COUNCIL_DISTRICT	CENSUS_TRACT	NTA_NAME
0	BROOKLYN	3057705	1084	FULTON STREET	321953891	2	A2	N	2016	20	...	NaN	NaN	7.183871e+09	11/22/2023 00:00:00	3967198	40.681528	-73.957603	36.0	227.0	Clinton Hill
1	BROOKLYN	3166244	24	BAY 11TH STREET	340905275	1	A2	N	6361	51	...	NaN	NaN	3.474747e+09	11/22/2023 00:00:00	3967199	40.609957	-74.008655	43.0	172.0	Bath Beach
2	STATEN ISLAND	5052978	307	NAUGHTON AVE	540246134	1	A2	N	3652	60	...	NaN	NaN	9.178367e+09	05/02/2023 00:00	3948737	40.583785	-74.093882	50.0	11201.0	Old Town-Dongan Hills-South Beach
3	STATEN ISLAND	5172013	48	HENDRICKS AVENUE	540249337	1	A2	N	39	29	...	NaN	NaN	9.172578e+09	05/02/2023 00:00	3948738	40.640468	-74.083137	49.0	11.0	West New Brighton-New Brighton-St. George
4	BROOKLYN	3108295	59	EAST 40 STREET	340906087	1	A2	N	4861	51	...	NaN	NaN	3.472285e+09	11/22/2023 00:00:00	3967200	40.654432	-73.940354	41.0	814.0	East Flatbush-Farragut

	Unique Key	Created Date	Closed Date	Agency	Agency Name	Incident Zip	Incident Address	Street Name	Cross Street 1	Cross Street 2	...	Y Coordinate (State Plane)	Open Data Channel Type	Latitude	Longitude	Location	Month	Weekday	Time	Adjusted Date	Complaints Count
0	15628757	2010-01-01 00:08:02	2010-01-01 03:53:37	NYPD	New York City Police Department	11220.0	876 58 STREET	58 STREET	8 AVENUE	9 AVENUE	...	170882.0	PHONE	40.635708	-74.006853	(40.635707991592696, -74.00685286309795)	1	4	728	2009-12-31	1
1	15627442	2010-01-01 00:08:29	2010-01-01 00:27:41	NYPD	New York City Police Department	10036.0	317 WEST 45 STREET	WEST 45 STREET	8 AVENUE	9 AVENUE	...	215978.0	PHONE	40.759486	-73.989135	(40.75948567983112, -73.98913488475046)	1	4	728	2009-12-31	1
2	15628369	2010-01-01 00:15:12	2010-01-01 02:35:35	NYPD	New York City Police Department	10014.0	333 WEST 11 STREET	WEST 11 STREET	GREENWICH STREET	WASHINGTON STREET	...	207278.0	PHONE	40.735607	-74.007697	(40.735606621969815, -74.00769667288294)	1	4	735	2009-12-31	1
3	15628147	2010-01-01 00:19:07	2010-01-01 08:31:26	NYPD	New York City Police Department	10453.0	1702 GRAND AVENUE	GRAND AVENUE	WEST 175 STREET	WEST 176 STREET	...	248407.0	PHONE	40.848463	-73.914058	(40.84846286296289, -73.91405798979748)	1	4	739	2009-12-31	1
4	15628798	2010-01-01 00:27:45	2010-01-01 01:53:10	NYPD	New York City Police Department	11218.0	430 OCEAN PARKWAY	OCEAN PARKWAY	CORTELYOU ROAD	DITMAS AVENUE	...	171701.0	PHONE	40.637953	-73.973088	(40.63795302715787, -73.97308845571062)	1	4	747	2009-12-31	1

	ZCTA5CE10	INTPTLAT10	INTPTLON10	geometry	Incident Zip	NoiseComplaints	selected
121	10467	+40.8699533	-073.8656955	POLYGON ((-73.88486 40.87855, -73.87986 40.868...	10467	29255	True
95	11221	+40.6913401	-073.9278789	POLYGON ((-73.92759 40.70176, -73.93026 40.698...	11221	29116	True
31	11226	+40.6464480	-073.9566488	POLYGON ((-73.94651 40.64010, -73.94726 40.656...	11226	28210	True
122	10458	+40.8625453	-073.8881454	POLYGON ((-73.87986 40.86827, -73.88486 40.878...	10458	27962	True
72	10468	+40.8689655	-073.8999436	POLYGON ((-73.88486 40.87855, -73.88711 40.882...	10468	27901	True

1. Motivation¶

1.1. About dataset¶

1.2. Why we chose those datasets¶

1.3. Goal for the end user's experience¶

2. Basic stats¶

2.1. Data cleaning and preprocessing¶

NYC 311 House Party Noise Complaints from 2010 to 2023¶

NYC 311 Noise Complaints from 2023¶

Department of Building (DOB) Permit Data.¶

3. Data Analysis¶

House Parties¶

Construction work noise complaints¶

Combining Permit Data and NYC 311 dataset.¶

Load the custom dataset.¶

4. Genre¶

4.1. Visual narrative tools¶

4.2. Narrative structure tools¶

5. Visualizations¶

6. Discussion¶

7. Contributions¶

References¶